The Agent Skills Directory

[COMMAND_EXECUTION]: The skill employs standard development tools including git log, git blame, and grep to examine repository history and local documentation. These operations are restricted to the local filesystem and are consistent with the skill's stated purpose.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from external sources.
Ingestion points: Git commit messages, repository source code, and local log files located in docs/log/*.md are read into the agent's context.
Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the ingested data.
Capability inventory: The skill's capabilities are limited to reading repository data and issue logs using git, grep, and glob. It does not perform network writes or execute arbitrary code.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the history or logs before it is processed by the agent.

review-history